Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 2962 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.1680. Min Range: -0.1680

Max Act: 0.1680. Min Act: -0.0000

Data Index: 1639960 (Python Code)

Max Activating Token Index: 658

Text #1

Max Range: 0.1680. Min Range: -0.1680

Max Act: 0.1489. Min Act: -0.0000

Data Index: 1578913 (Python Code)

Max Activating Token Index: 481

Text #2

Max Range: 0.1680. Min Range: -0.1680

Max Act: 0.1318. Min Act: -0.0000

Data Index: 1468925 (Python Code)

Max Activating Token Index: 877

Text #3

Max Range: 0.1680. Min Range: -0.1680

Max Act: 0.1106. Min Act: -0.0000

Data Index: 1513514 (Python Code)

Max Activating Token Index: 238

Text #4

Max Range: 0.1680. Min Range: -0.1680

Max Act: 0.1148. Min Act: -0.0000

Data Index: 1596071 (Python Code)

Max Activating Token Index: 326

Text #5

Max Range: 0.1680. Min Range: -0.1680

Max Act: 0.1159. Min Act: -0.0000

Data Index: 1585800 (Python Code)

Max Activating Token Index: 320

Text #6

Max Range: 0.1680. Min Range: -0.1680

Max Act: 0.1030. Min Act: -0.0000

Data Index: 1587847 (Python Code)

Max Activating Token Index: 609

Text #7

Max Range: 0.1680. Min Range: -0.1680

Max Act: 0.1051. Min Act: -0.0000

Data Index: 1359893 (Python Code)

Max Activating Token Index: 356

Text #8

Max Range: 0.1680. Min Range: -0.1680

Max Act: 0.1066. Min Act: -0.0000

Data Index: 1410333 (Python Code)

Max Activating Token Index: 408

Text #9

Max Range: 0.1680. Min Range: -0.1680

Max Act: 0.1136. Min Act: -0.0000

Data Index: 1487094 (Python Code)

Max Activating Token Index: 292

Text #10

Max Range: 0.1680. Min Range: -0.1680

Max Act: 0.1058. Min Act: -0.0000

Data Index: 1521737 (Python Code)

Max Activating Token Index: 417

Text #11

Max Range: 0.1680. Min Range: -0.1680

Max Act: 0.1087. Min Act: -0.0000

Data Index: 1392240 (Python Code)

Max Activating Token Index: 902

Text #12

Max Range: 0.1680. Min Range: -0.1680

Max Act: 0.0954. Min Act: -0.0000

Data Index: 1515285 (Python Code)

Max Activating Token Index: 601

Text #13

Max Range: 0.1680. Min Range: -0.1680

Max Act: 0.1025. Min Act: -0.0000

Data Index: 1472857 (Python Code)

Max Activating Token Index: 194

Text #14

Max Range: 0.1680. Min Range: -0.1680

Max Act: 0.1132. Min Act: -0.0000

Data Index: 1391878 (Python Code)

Max Activating Token Index: 990

Text #15

Max Range: 0.1680. Min Range: -0.1680

Max Act: 0.0975. Min Act: -0.0000

Data Index: 1363810 (Python Code)

Max Activating Token Index: 562

Text #16

Max Range: 0.1680. Min Range: -0.1680

Max Act: 0.0996. Min Act: -0.0000

Data Index: 1509706 (Python Code)

Max Activating Token Index: 549

Text #17

Max Range: 0.1680. Min Range: -0.1680

Max Act: 0.0973. Min Act: -0.0000

Data Index: 1541315 (Python Code)

Max Activating Token Index: 690

Text #18

Max Range: 0.1680. Min Range: -0.1680

Max Act: 0.0970. Min Act: -0.0000

Data Index: 1542234 (Python Code)

Max Activating Token Index: 831

Text #19

Max Range: 0.1680. Min Range: -0.1680

Max Act: 0.0960. Min Act: -0.0000

Data Index: 1461813 (Python Code)

Max Activating Token Index: 877